INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iy

-0.75

 nights

-0.71

iffe

-0.70

gi

-0.65

agement

-0.64

oni

-0.64

eki

-0.64

res

-0.64

 indexed

-0.63

ippi

-0.62

POSITIVE LOGITS

Pod

0.72

sonian

0.72

 Lanka

0.70

å

0.69

ulhu

0.69

agascar

0.65

¶æ

0.65

©¶æ

0.65

 Inqu

0.65

Discuss

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.